Re: single aio thread is migrated crazily by scheduler

[Dave Chinner]

On Mon, Dec 09, 2019 at 10:21:22PM +0530, Srikar Dronamraju wrote:
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index 44123b4d14e8..efd740aafa17 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -2664,7 +2664,12 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
>   */
>  int wake_up_process(struct task_struct *p)
>  {
> -	return try_to_wake_up(p, TASK_NORMAL, 0);
> +	int wake_flags = 0;
> +
> +	if (is_per_cpu_kthread(p))
> +		wake_flags = WF_KTHREAD;
> +
> +	return try_to_wake_up(p, TASK_NORMAL, WF_KTHREAD);

This is buggy. It always sets WF_KTHREAD, even for non-kernel
processes. I think you meant:

	return try_to_wake_up(p, TASK_NORMAL, wake_flags);

I suspect this bug invalidates the test results presented, too...

-Dave.
-- 
Dave Chinner
david@xxxxxxxxxxxxx